Global Exponential Stability of Recurrent Neural Networks with Time-Dependent Switching Dynamics

Authors:
Zhigang Zeng;Jun Wang;Tingwen Huang
Affiliations:
Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan, China 430074;Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong;Texas A&M University at Qatar, Doha, Qatar
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Year:
2009

Citing 5
Cited 0

Lie-Algebraic Stability Criteria for Switched Systems

SIAM Journal on Control and Optimization
Almost sure exponential stability of recurrent neural networks with Markovian switching

IEEE Transactions on Neural Networks
Robust Stability of Switched Cohen–Grossberg Neural Networks With Mixed Time-Varying Delays

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Brief Stability analysis of digital feedback control systems with time-varying sampling periods

Automatica (Journal of IFAC)
Noise-Induced Stabilization of the Recurrent Neural Networks With Mixed Time-Varying Delays and Markovian-Switching Parameters

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the switching dynamics of recurrent neural networks are studied. Sufficient conditions on global exponential stability with an arbitrary switching law or a dwell time switching law and the estimates of Lyapunov exponent are obtained. The obtained results can be used to analyze and synthesize a family of continuous-time configurations with the switching between the configurations. Specially, the obtained results are new and efficacious for the switching between the stable and unstable configurations. Finally, simulation results are discussed to illustrate the theoretical results.